Method and system for automatic speech recognition

Abstract

An automatic speech recognition method includes at a computer having one or more processors and memory for storing one or more programs to be executed by the processors, obtaining a plurality of speech corpus categories through classifying and calculating raw speech corpus; obtaining a plurality of classified language models that respectively correspond to the plurality of speech corpus categories through a language model training applied on each speech corpus category; obtaining an interpolation language model through implementing a weighted interpolation on each classified language model and merging the interpolated plurality of classified language models; constructing a decoding resource in accordance with an acoustic model and the interpolation language model; and decoding input speech using the decoding resource, and outputting a character string with a highest probability as a recognition result of the input speech.

Description

RELATED APPLICATIONS[0001]This application is a continuation application of PCT Patent Application No. PCT / CN2013 / 086707, entitled “METHOD AND SYSTEM FOR AUTOMATIC SPEECH RECOGNITION” filed on Nov. 7, 2013, which claims priority to Chinese Patent Application No. 201310033201.7, “METHOD AND SYSTEM FOR AUTOMATIC SPEECH RECOGNITION,” filed on Jan. 29, 2013, both of which are hereby incorporated by reference in their entirety.FIELD OF THE INVENTION[0002]The present invention relates to the technical field of Automatic Speech Recognition (ASR), especially relates to a method and system for automatic speech recognition.BACKGROUND OF THE INVENTION[0003]Automatic speech Recognition technology is a sort of technology which transforms the lexical content of human speech into input characters that can be read by computers. The speech recognition has a complicated processing flow, mainly including four processes of acoustic model training, language model training, decoding resource constructing...

AI Technical Summary

Benefits of technology

The patent describes an automatic speech recognition system that uses a combination of linguistic and acoustic models to recognize speech. The system includes a computer with processors and memory, a classifying process module, a language model training module, a weight merging module, a resource construction module, and a decoder. The system obtains speech corpus categories by classifying and calculating raw speech corpus, and then uses these categories to train language models that correspond to them. The system also uses an interpolation language model that is obtained through a weighted interpolation of the language models. The system decodes input speech using the trained language models and outputs a character string with the highest probability as a recognition result. The technical effect of this system is that it improves the accuracy and efficiency of speech recognition.

Problems solved by technology

However, most of the conventional speech recognition technology is based on the universal speech recognition application that constructs the model for the common speech recognition, in this situation, the training corpus of language model is based on the data collection and actual input of users, though it reflects well the speech habits of the users to some extent and often has a better recognition effect for the daily expression, because of less frequent obscure words in the training corpus of the language model, such as medicine name, place name, etc., it can't form an effective probability statistics model, the probability value of the character string corresponding to the obscure words in the language model is very low, so when it needs to recognize the obscure words spoken by the user, a problem of data offset often happens, it means the recognized character string is not the words spoken by the user, in other words, the recognition accuracy for the speech of the obscure words is lower, thus it is difficult to achieve a better recognition result.

Images